Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    renheit
    -0.79
    estate
    -0.76
    ibur
    -0.76
    ioxide
    -0.76
    ITNESS
    -0.75
    QUEST
    -0.71
    sec
    -0.70
    jiang
    -0.70
    arent
    -0.69
    Herm
    -0.68
    POSITIVE LOGITS
    abouts
    0.69
     axe
    0.69
     shores
    0.66
     lion
    0.66
     crowds
    0.66
     immortal
    0.64
    ĪĴ
    0.60
    comings
    0.58
     Arrow
    0.58
     Cth
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.